Publications

Neural and Evolutionary Computing

LEVERAGING EDGE DETECTION AND NEURAL NETWORKS FOR BETTER UAV LOCALIZATION

We propose a new method for the geolocalization of Unmaned Aerial Vehicles (UAV) in environments without Global Navigation Stallite Systems (GNSS). Current stateof-the-art methods use an offline-trained encoder to compute a vector representation …

Théo Di Piazza, Enric Meinhardt-Llopis, Gabriele Facciolo, Bénédicte Bascle, Corentin Abgrall, Jean-Clément Devaux

2024 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2024) - 2024

Machine Learning

De l'apprentissage fédéré vers une théorie critique de l'apprentissage hétéromatique

This manuscript attests to a significant epistemological swing. This document consists of two sections: the first relates to mathematics --- the initial discipline in which this thesis began --- and the second to Sciences and Technologies Studies …

Marie Garin

Mathematics

On the Domain Generalization Capabilities of Interactive Segmentation Methods

Interactive image segmentation (IIS) methods are usually trained over segmentation datasets containing natural images. They are also usually evaluated over natural images. However, the most common use case is the annotation of new images from a…

Franco Marchesoni-Acland, Tanguy Magne, Fayçal Rekbi, Gabriele Facciolo

Image Processing On Line - 2024

Physics

How Shock ignition can help to overcome the negative effects of hot electrons in direct-drive high-gain inertial confinement fusion

Hot electrons produced by parametric instabilities can negatively affect the thermonuclear gain of a direct-drive inertial confinement fusion capsule. A Monte Carlo transport is coupled to the hydrodynamics MULTI-IFE code in order to study the hot…

Mauro Temporal, Benoit Canaud, Rafael Ramis

Journal of Plasma Physics - 2024

Mathematics

Accelerating NeRF with the Visual Hull

Neural rendering methods for learning the appearance and geometry of 3D scenes have gained tremendous popularity since 2020. In this field, NeRF or Neural Radiance Fields is the bestknown methodology. Given a collection of multi-view images and…

Roger Marí

Image Processing On Line - 2024

Computer Science

Survival Forest for Left-Truncated Right-Censored Data

The estimation of the lifetime of an industrial equipment or a patient is often based on censored data, because the event of interest is observed only for a subsample of observations. The use of the Random Forest algorithm applied to industrial data…

Vincent Laurent, Olivier Vo Van

Image Processing On Line - 2024

Mathematics

Dehazing with Dark Channel Prior: Analysis and Implementation

In outdoor scenes, atmospheric absortion and scattering attenuate the radiance received by the camera and may produce haze. In 2009 He et al. proposed a simple but effective dehazing algorithm based on a hypothesis called the 'dark channel prior' …

Jose-Luis Lisani, Charles Hessel

Image Processing On Line - 2024

Computer Science

Image Forgery Detection Based on Noise Inspection: Analysis and Refinement of the Noisesniffer Method

Images undergo a complex processing chain from the moment light reaches the camera's sensor until the final digital image is delivered. Each of its operations leaves traces on the noise model which enable forgery detection through noise analysis. In…

Marina Gardella, Pablo Musé, Miguel Colom, Jean-Michel Morel

Image Processing On Line - 2024

Computer Science

Comparing Interactive Image Segmentation Models under Different Clicking Procedures

Interactive image segmentation (IIS) methods are usually evaluated in terms of segmentation performance vs. number of clicks (NoC). However, the automatic evaluation depends on a clicking procedure and its relation to the procedure used for training…

Franco Marchesoni-Acland

Image Processing On Line - 2024

Mathematics

A Review of t-SNE

Sangwon Jung, Tristan Dagobert, Jean-Michel Morel, Gabriele Facciolo

Image Processing On Line - 2024